{
  "markdown": "# pdf-tables-mcp\n\n**Reliable PDF table extraction as an MCP tool.** Drop into Claude, Cursor, or any MCP-compatible agent and get clean structured JSON tables back from any PDF — with per-cell citations to the source page.\n\nBuilt by [Tool Factory](https://github.com/mehtaphysical13) — Tool #2.\n\n🚧 **v0.1 scaffold** — tools coming online over the next few days.\n\n## What it does\n\nAgents drop a PDF URL, get back clean structured JSON tables with confidence scores and cell-level citations back to the source page.\n\nUse cases:\n- RAG preprocessing: split tables from text-heavy docs\n- Agentic data extraction from financial filings, scientific papers, gov reports\n- Form-field reading in compliance workflows\n- Receipt/invoice line-item parsing\n\n## Pricing\n\n| Tier | Price | Quota (pages/mo) |\n|---|---|---|\n| Free | $0 | 50 pages |\n| Hobby | $19/mo | 250 pages |\n| Pro | $99/mo | 2,000 pages |\n| Business | $499/mo | 15,000 pages, 99.9% SLA |\n| Enterprise | Custom | Unlimited, VPC, SOC 2 path |\n\nQuotas measure pages processed (not calls) — a 3-page PDF counts as 3 against your monthly quota. Keeps pricing fair for users running small and large PDFs alike.\n\n## Install (coming soon)\n\n```jsonc\n{\n  \"mcpServers\": {\n    \"pdf-tables\": {\n      \"url\": \"https://pdf-tables-mcp.vercel.app/api/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer pdt_live_YOURKEY\"\n      }\n    }\n  }\n}\n```\n\n## License\n\nMIT\n",
  "bytes": 1405,
  "sha": "47af69d2437abca54366109a481a37f8fa383faac890b4b9043af351b4f6afbf",
  "repo_slug": "mehtaphysical13/pdf-tables-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_mehtaphysical13_pdf_tables_mcp_3a2483e6/readme"
}